© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95724
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bonté
    -0.77
     feroit
    -0.69
     varandra
    -0.69
     pouvoit
    -0.68
     république
    -0.67
     partenza
    -0.66
     démocratie
    -0.66
     igång
    -0.65
     auroit
    -0.65
     atteinte
    -0.65
    POSITIVE LOGITS
     enough
    0.93
     disambiguazione
    0.88
    antd
    0.66
     demand
    0.56
    RefNanny
    0.54
     popular
    0.54
    EndContext
    0.54
    PerformLayout
    0.53
     sufficient
    0.52
     murid
    0.52
    Activations Density 0.070%

    No Known Activations